From Graphs to Gradients: Physics-Inspired Structural Attribution for Cyber-Physical IoT Systems and Beyond

从图模型到梯度：面向信息物理物联网系统及其他领域的物理启发式结构归因

Abstract: Interpretable explanation methods in Artificial Intelligence aim to uncover the underlying causes and their effects, enabling a deeper understanding of why a system behaves in a certain way under different inputs. 摘要： 人工智能中的可解释性方法旨在揭示潜在的因果关系及其影响，从而使用户能够更深入地理解系统为何在不同输入下表现出特定的行为。

Unlike traditional explainability methods, which mainly highlight correlations between input and output variables, causal explanation focuses on interventional questions. By doing so, it provides more robust insights, helping users understand automated decisions, especially in high-risk domains. 与主要强调输入和输出变量之间相关性的传统可解释性方法不同，因果解释侧重于干预性问题。通过这种方式，它提供了更稳健的见解，帮助用户理解自动化决策，特别是在高风险领域。

Recovering an explicit directed causal structure, however, is often impractical in large-scale, hybrid cyber-physical systems with feedback loops and partial observability. This paper introduces a novel framework inspired by statistical mechanics that instead models variable dependencies through an undirected, energy-based representation of cyber-physical IoT systems. 然而，在具有反馈回路和部分可观测性的大规模混合信息物理系统中，恢复明确的有向因果结构往往是不切实际的。本文引入了一种受统计力学启发的新型框架，通过信息物理物联网系统的无向、基于能量的表示来建模变量依赖关系。

Our approach enables rigorous dependency-aware attribution by analysing how variations in the energy landscape reflect the influence of individual components, without recovering a directed causal graph. It also supports reasoning about perturbation effects across hybrid interactions, providing reliable explanations of abnormal behaviours. 我们的方法通过分析能量景观的变化如何反映各个组件的影响，实现了严谨的依赖感知归因，而无需恢复有向因果图。它还支持对混合交互中的扰动效应进行推理，从而为异常行为提供可靠的解释。

We empirically examined our framework through simulations on an industrial IoT testbed with hybrid continuous and discrete variables, demonstrating higher attribution accuracy, improved robustness and better scalability than state-of-the-art graph-based approaches. 我们通过在包含混合连续和离散变量的工业物联网测试平台上进行模拟，对该框架进行了实证检验。结果表明，与最先进的基于图的方法相比，该框架具有更高的归因准确性、更强的鲁棒性和更好的可扩展性。

While the attributions are not intended to fully recover the system’s generative dynamics, they provide valuable, dependency-aware explanations supporting both human interpretation and downstream predictive and diagnostic tasks. Although demonstrated in industrial IoT security, our framework also applies to other high-dimensional cyber-physical and socio-technical systems requiring principled, structural explanations. 虽然这些归因并非旨在完全恢复系统的生成动力学，但它们提供了有价值的、依赖感知的解释，支持人类理解以及下游的预测和诊断任务。尽管该框架是在工业物联网安全领域进行演示的，但它同样适用于其他需要原则性结构解释的高维信息物理系统和社会技术系统。